AI-900 Practice Question: Describe features of generative AI workloads on Azure
What are embeddings in the context of AI and language models?
⚠ Common exam trap
Candidates often confuse the general term 'embedding' (as in integrating AI into apps) with the specific NLP concept of vector embeddings, leading them to pick Option A.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Numerical vector representations of text that capture semantic meaning
Embeddings are dense numerical vector representations of text that capture semantic meaning, enabling language models to understand relationships between words and phrases. In the context of AI and language models, embeddings map words, sentences, or documents to high-dimensional vectors where similar meanings are closer in vector space, which is fundamental for tasks like semantic search, clustering, and transfer learning.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
The process of inserting AI capabilities into existing applications
Why it's wrong here
This option describes AI integration, where APIs or machine-learning models are added to existing software to augment its functionality. In contrast, an 'embedding' in ML is a numeric vector produced by a model to represent input data (like text) in a continuous vector space. The term 'embed' can mean to include something, but in AI the technical meaning is specifically a learned mathematical representation, not a software engineering process.
- ✓
Numerical vector representations of text that capture semantic meaning
Why this is correct
Embeddings are dense, high-dimensional vector representations of text (or other data) that encode semantic meaning based on learned patterns. During training, models such as BERT or Word2Vec map words and sentences so that items with similar meaning end up with similar numerical vectors, measurable by distance metrics like cosine similarity. This property enables semantic search, clustering, and other meaning-based operations.
- ✗
The training dataset used to build a language model
Why it's wrong here
The training dataset is the raw text corpus (e.g., books or web pages) on which a model learns statistical patterns. Embeddings are the learned outcome of that process: the model's encoder translates each input token or phrase into a fixed-length vector. Mistaking the dataset for the embeddings reverses cause and effect, as embeddings are a representation derived from the data, not the data itself.
- ✗
Compressed versions of large language models for edge deployment
Why it's wrong here
Compressing large language models for edge deployment is a model optimization process, typically using quantization, pruning, or knowledge distillation. Embeddings are not compressed versions of a model; rather, they are the vector outputs that a model generates for input tokens. A compressed model still produces embeddings, but the embeddings themselves are independent data representations, not the model.
Go deeper
Related to this question
Learn chapter
Machine Learning Core Concepts
Key term
Semantic search
Semantic search is a search method that understands the intent and contextual meaning of a user's query, rather than just matching exact keywords.
Key term
Clustering
Clustering is a technique where multiple servers work together as a single system to keep applications running even if one server fails.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.